INDEX

Explanations

references to numerical data, particularly statistics and figures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.03

2:0.05

3:0.05

4:0.06

5:0.04

6:0.46

7:0.03

8:0.04

9:0.04

10:0.08

11:0.05

Negative Logits

��

-1.71

 omission

-1.53

 gateway

-1.47

hower

-1.39

worldly

-1.35

¯

-1.34

Bok

-1.28

 sourcing

-1.28

azy

-1.28

 backdoor

-1.27

POSITIVE LOGITS

glers

1.38

Ct

1.34

pound

1.33

 Percent

1.32

birth

1.31

cies

1.29

tips

1.29

illion

1.28

Adult

1.27

Foot

1.26

Activations Density 0.135%

references to numerical data, particularly statistics and figures

No Comments

No Known Activations